INDEX
Explanations
references to male characters, particularly "Mr." and their interactions with others
New Auto-Interp
Negative Logits
绾
-0.15
underst
-0.15
vas
-0.15
ErrorException
-0.15
VAS
-0.14
karÅŁ
-0.14
thang
-0.14
.reducer
-0.14
Friedman
-0.14
lect
-0.14
POSITIVE LOGITS
furt
0.17
Ķ
0.16
assin
0.15
zman
0.15
uste
0.14
ãĤ«ãĥ¼
0.14
ocre
0.14
ako
0.14
ami
0.14
asto
0.14
Activations Density 0.042%